@daniel_mac8 Benchmarks are just like gym PRs for AI. Great for the leaderboard, but doesn't tell you if it can actually carry the groceries without dropping them.
English
DC｜use.fo
1.7K posts
DC｜use.fo
@vibecoder_dc
Building @usedotfo: Next-gen AI Voice Typing. 🎙️ Vibe Coder | AI & Blockchain Specialist. Serial Founder. Turning intent into logic at the speed of thought. ⚡
Beigetreten Nisan 2024
102 Folgt5.5K Follower
Grok 4.5 is a "Wow!" moment. 🤯
> Opus 4.8 & GPT-5.5 level on benchmarks
> Costs less than Sonnet 5
Is that real? Hard to believe.
Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5.
Use Fable as the orchestrator and a combo of:
1. Grok 4.5
2. Opus 4.8
3. GPT-5.5
As implementer agents.
Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.
English
@RoundtableSpace This is like saying the secret to a fast car isn't the engine, it's the chassis. True, but if the engine is a lawnmower, no amount of aero helps.
English
Sonnet 5 loses to Opus 4.8 on benchmarks. But this happens when you pair them.
Set Sonnet 5 as the implementer, Fable 5 as the advisor, Fast & cheap execution, frontier-level reasoning
The real unlock isn't the model. It's the stack.
English
DC｜use.fo retweetet
RL isn't hitting its limits anytime soon!
Love how SWE-1.7 uses a fraction of the cost compared to the frontier models to get these results. This is the kind of crazy stuff that I am seeing frontier open models (e.g., Kimi 2.7) are starting to enable.
Cognition@cognition
Introducing SWE-1.7, the most capable model we’ve trained yet. It scores within a few points of the strongest frontier models at a fraction of the cost, and is now available at 1000 tok/s. RL is not hitting its limit: after refining our recipe, we keep seeing gains as we scale
English
Losing access to Chinese Open Weight models would put tremendous pressure on Nvidia's open source team.
Even Nvidia's used Chinese Open Weight models for their own developments.
Why go down this road? Isn't the world already closed enough as it is?
righttointelligence.org
Jukan @ ICML@jukan05
CHINA CONSIDERS RESTRICTING OVERSEAS ACCESS TO CUTTING-EDGE AI MODELS China’s Ministry of Commerce has led meetings over the past month with major AI companies, including Alibaba, ByteDance, and Z.ai, to discuss measures that would restrict overseas access to cutting-edge AI models, including models that have not yet been released. The discussions reportedly include not only closed-source models but also open-weight models. However, the scope of application is still under debate, and the rules may ultimately apply only to future frontier models. Officials have also discussed designating the leakage or theft of proprietary AI technologies as a national security crime, with stronger penalties, as well as restricting the types of foreign capital that can invest in Chinese AI startups. The backdrop is the U.S. move to strengthen export controls on AI models, along with national security concerns over cutting-edge models that could possess advanced cyberattack capabilities. Chinese authorities are reportedly concerned that advanced U.S. cybersecurity AI models could be used to exploit vulnerabilities in Chinese software. Since the beginning of this year, China has continued to tighten measures to prevent AI technology from being transferred overseas. Authorities have investigated whether Chinese AI startups that relocated abroad violated export control laws, while also strengthening oversight of overseas transactions involving Chinese investors, technology, data, and national security concerns. Future regulations could take the form of a tiered framework based on technological capability. Basic open-source AI models may be managed through a filing system, high-performance models may be subject to security reviews, and the most sensitive frontier models may be banned from public release or restricted to use within China.
English
DC｜use.fo retweetet
Claude Fable wrote a FlashAttention forward kernel in pyptx DSL for the NVIDIA B200 (Blackwell) that runs at 0.92–0.99× of FlashAttention-4, the hand-tuned CUTLASS kernel — parity on two sequence lengths, ~1350 TFLOPS bf16.
It's written in pyptx, my Python DSL that emits raw PTX. No CUDA C++, no CUTLASS.
Out of the box, Claude Code + Fable hit 0.71× (878 TFLOPS). An improved harness I built for this task let Fable close the rest.
tcgen05 tensor cores, TMEM, warp specialization, mbarrier pipelines — all from Python.
English
iPad/Tailscale/Termius/Hermes
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 loaded in
I must keep learning so im deep diving into inference optimizations
Vocabulary you see around but might know what it is like PP, TP, and EP
When you know some of these fundamentals, it's different when you moving around local ai.
English
Sure, Sonnet 5 loses to Opus 4.8 on benchmarks.
But the real unlock isn't the model, it's the stack!
You mix them in Claude Code to merge frontier intelligence with practical efficiency.
Here is how to configure it:
> The Advisor: Let Fable 5 handle frontier-level reasoning and strategy.
> The Implementer: `Run /model set to Sonnet 5` for fast, cheap execution.
> The Workflow: Run `/effort set to Ultracode` to trigger dynamic workflows for complex tasks.
With this pairing, Fable becomes your superintelligent brain, and Sonnet becomes the hands rapidly typing the code 🧠
English
DC｜use.fo retweetet
Huge: China’s MiniMax Plans to Launch 2.7-Trillion Parameter Model (MiniMax Pro)
tl;dr MiniMax is preparing a 2.7T parameter open-source model, potentially launching as early as Q3.
That would make it far larger than any Chinese model currently on the market, and over 6x bigger than MiniMax’s current M3 model.
China’s open-source AI wave is not slowing down. Looks like they just started.
Via The Information
English
@PawelHuryn This is essentially the 'Manager vs Worker' architecture. Using an executor as an orchestrator is like asking a middle manager to do the actual coding. Better to have the CEO set the strategy and let the devs execute.
English
I doubt anyone wants to run Sonet as an orchestrator. A better way is to start with Opus and delegate down or escalate to Fable:
ClaudeDevs@ClaudeDevs
A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.
English
DC｜use.fo retweetet
Huggingface put 106 agents on optimising Gemma-4 inference. Watch it go woosh
huggingface.co/spaces/agent-c…
English
China gave its models away when it was behind.
Qwen, DeepSeek, GLM. All were open. The strategy was to commoditize the model layer so US labs can't charge premium prices.
It worked. US companies now route over 30% of their AI tokens through Chinese models every week (a year ago that was 11%).
Now Chinese models are roughly 6 to 9 months behind the US frontier instead of years. And this week it's reported that Beijing is discussing restricting overseas access to its best models for the first time.
The logic is pretty simple. You give the model away when you're second. You restrict it when you think you're about to be first.
Ethan Mollick@emollick
This is a key reason I don’t expect the flow of frontier open weights models to continue indefinitely, or even for very much longer. reuters.com/world/beijing-…
English
DC｜use.fo retweetet
82.8 tp here! MTPLX v2 Qwen 3.6 27B Optimized Speed!
Pushing to the Max combined with colder temperatures outside 🔥
Gonna post comparisons vs DGX Spark, but there is no match here, Youssof cooked really hard on this release!
Youssof Al Toukhi@Youssofal_
72+ TPS on Qwen 3.6 27B on a Macbook pro M5 max. MTPLX V2 out now! The fastest way to run models on MLX.
English
Don't do this!
> Fable 5 as orchestrator + advisor
> GPT 5.5 as executor
> Sonnet 5 as "nothing"
Sonnet 5 is nowhere near GPT 5.5 in terms of reasoning power, execution, code quality, long-horizon tasks, and the list can go on and on.
Give respect where it's due!
ClaudeDevs@ClaudeDevs
A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.
English
DC｜use.fo retweetet
The Summer GPT-5.6 Sol-stice kicks of tomorrow.
What we know:
> Beats Fable on TerminalBench 2.1
> Cerebras serves it at 750 tok/s
> $30/mil tok output vs. $50 for Fable
@skirano says it's "the best model" he's ever used.
Tomorrow, we worship the sun.
OpenAI@OpenAI
GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday. We’re expanding preview access globally now.
English
@HowToPrompt__ Optimization without parameter updates is just building a better gearbox for a smoking engine. You're not fixing the combustion, just the delivery.
English
Microsoft made ChatGPT's accuracy jump from 41% to 80% without touching a single parameter.
The system is called SkillOpt.
Most people think AI agents improve by writing better prompts or fine-tuning the model itself. But fine-tuning is rigid, slow, and expensive. And "prompt engineering" is just guessing.
Microsoft’s approach treats the AI’s skill set, the actual text document that tells it how to solve a problem, as a living, breathing model that learns from its own failures.
Here is how it works:
1. Rollouts: The agent attempts tasks. It captures its own successes and failures.
2. Optimizer Model: A separate, small model analyzes those results and makes atomic edits to the skill document (Add, Delete, or Replace).
3. Validation Gate: The new skill is only "accepted" if it strictly improves performance on a held-out set of tasks.
It is essentially "Gradient Descent" for natural language.
And the results are staggering:
Across six major benchmarks, SkillOpt outperformed every human-written skill and every one-shot LLM approach.
On some tasks, accuracy skyrocketed. On the ALFWorld benchmark, one model jumped from 70% to 85% accuracy. In direct chat scenarios, it boosted accuracy by over 23 points.
The best part?
There is zero inference-time overhead.
You spend the compute optimizing the skill once. Then, the agent runs with that hyper-optimized playbook forever.
The playbook effectively "trains" itself through feedback.
If you want an agent that actually gets better at its job every single day, without you having to touch a single line of code, this is how it’s done.
English
DC｜use.fo retweetet
Embodied.cpp
A portable C++ inference runtime for embodied AI models on heterogeneous robots.
It runs both VLA and world-action models on CPU, GPU, or NPU with GGUF weights for edge-side robotic control.
English
DC｜use.fo retweetet
I sped up deepseek v4 flash by 29x on my 4x3090s !!!
No, its not joke.
15 -> 443 t/s. a 23k prompt used to take 25 mins. Now it takes 53 secs. 284b in 2bit, 87gb, barely squeezes into 96gb.
Me and Fable 5 spent 4 days in llama.cpp. Fixed everything that was broken
English
DC｜use.fo retweetet
Standford just built the agent-native version of Git.
It’s called Shepherd. It turns every agent run into a Git-like trace you can fork, replay, or revert.
→ ctrl+Z any AI agent action
→ 5x faster than docker commit
→ 95% KV-cache reuse on replay
→ Runs Claude, offline mode, or any agent
100% Open Source.
English
DC｜use.fo retweetet
Tencent just released a reranker for agent skill routing on Hugging Face
Trained with rejected skill combinations as supervision,
the 0.6B cross-encoder reranks tool candidates so LLM agents pick compatible skills.
English